1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
|
%global _empty_manifest_terminate_build 0
Name: python-mydatapreprocessing
Version: 3.0.3
Release: 1
Summary: Library/framework for making predictions.
License: mit
URL: https://github.com/Malachov/mydatapreprocessing
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/63/b5/e4b0d97599501bed7d4b2a8340cff59de3caf288326fa39e9df8f1172ace/mydatapreprocessing-3.0.3.tar.gz
BuildArch: noarch
Requires: python3-mylogging
Requires: python3-mypythontools
Requires: python3-numpy
Requires: python3-pandas
Requires: python3-requests
Requires: python3-scipy
Requires: python3-sklearn
Requires: python3-typing-extensions
Requires: python3-wfdb
Requires: python3-openpyxl
Requires: python3-pyarrow
Requires: python3-pyodbc
Requires: python3-sqlalchemy
Requires: python3-tables
Requires: python3-xlrd
Requires: python3-wfdb
Requires: python3-openpyxl
Requires: python3-pyarrow
Requires: python3-pyodbc
Requires: python3-sqlalchemy
Requires: python3-tables
Requires: python3-xlrd
%description
# mydatapreprocessing
[](https://pypi.python.org/pypi/mydatapreprocessing/) [](https://badge.fury.io/py/mydatapreprocessing) [](https://pepy.tech/project/mydatapreprocessing) [](https://mybinder.org/v2/gh/Malachov/mydatapreprocessing/HEAD?filepath=demo.ipynb) [](https://lgtm.com/projects/g/Malachov/mydatapreprocessing/context:python) [](https://mydatapreprocessing.readthedocs.io/?badge=latest) [](https://opensource.org/licenses/MIT) [](https://codecov.io/gh/Malachov/mydatapreprocessing)
Load data from web link or local file (json, csv, Excel file, parquet, h5...), consolidate it (resample data, clean NaN values, do string embedding) derive new features via columns derivation and do preprocessing like
standardization or smoothing. If you want to see how functions works, check it's docstrings - working examples with printed results are also in tests - visual.py.
## Links
[Repo on GitHub](https://github.com/Malachov/mydatapreprocessing)
[Official readthedocs documentation](https://mydatapreprocessing.readthedocs.io)
## Installation
Python >=3.6 (Python 2 is not supported).
Install just with
```console
pip install mydatapreprocessing
```
There are some libraries that not every user will be using (for some specific data inputs for example). If you want to be sure to have all libraries, you can provide extras requirements like.
```console
pip install mydatapreprocessing[datatypes]
```
Available extras are ["all", "datasets", "datatypes"]
## Examples
You can use live [jupyter demo on binder](https://mybinder.org/v2/gh/Malachov/mydatapreprocessing/HEAD?filepath=demo.ipynb)
<!--phmdoctest-setup-->
```python
import mydatapreprocessing as mdp
import pandas as pd
import numpy as np
```
### Load data
You can use:
- python formats (numpy.ndarray, pd.DataFrame, list, tuple, dict)
- local files
- web urls
Supported path formats are:
- csv
- xlsx and xls
- json
- parquet
- h5
You can load more data at once in list.
Syntax is always the same.
<!--phmdoctest-label test_load_data-->
<!--phmdoctest-share-names-->
```python
data = mdp.load_data.load_data(
"https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv",
)
# data2 = mdp.load_data.load_data([PATH_TO_FILE.csv, PATH_TO_FILE2.csv])
```
### Consolidation
If you want to use data for some machine learning models, you will probably want to remove Nan values, convert string columns to numeric if possible, do encoding or keep only numeric data and resample.
Consolidation is working with pandas DataFrame as column names matters here.
There are many functions, but there is main function pipelining other functions `consolidate_data`
<!--phmdoctest-label test_consolidation-->
<!--phmdoctest-share-names-->
```python
consolidation_config = mdp.consolidation.consolidation_config.default_consolidation_config.do.copy()
consolidation_config.datetime.datetime_column = 'Date'
consolidation_config.resample.resample = 'M'
consolidation_config.resample.resample_function = "mean"
consolidation_config.dtype = 'float32'
consolidated = mdp.consolidation.consolidate_data(data, consolidation_config)
print(consolidated.head())
```
### Feature engineering
Functions in `feature_engineering` and `preprocessing` expects that data are in form (*n_samples*, *n_features*).
*n_samples* are usually much bigger and therefore transformed in `consolidate_data` if necessary.
In config, you can use shorter update dict syntax as all values names are unique.
### Feature engineering
Create new columns that can be for example used as another machine learning model input.
```python
import mydatapreprocessing.feature_engineering as mdpf
import mydatapreprocessing as mdp
data = pd.DataFrame(
[mdp.datasets.sin(n=30), mdp.datasets.ramp(n=30)]
).T
extended = mdpf.add_derived_columns(data, differences=True, rolling_means=10)
print(extended.columns)
print(f"\nit has less rows then on input {len(extended)}")
```
Functions in `feature_engineering` and `preprocessing` expects that data are in form (n_samples, n_features). n_samples are usually much bigger and therefore transformed in `consolidate_data`
if necessary.
### Preprocessing
Preprocessing can be used on pandas DataFrame as well as on numpy array. Column names are not important as it's just matrix with defined dtype.
There is many functions, but there is main function pipelining other functions `preprocess_data` Preprocessed data can be converted back with `preprocess_data_inverse`
<!--phmdoctest-label test_preprocess_data-->
<!--phmdoctest-share-names-->
```python
from mydatapreprocessing import preprocessing as mdpp
df = pd.DataFrame(np.array([range(5), range(20, 25), np.random.randn(5)]).astype("float32").T)
df.iloc[2, 0] = 500
config = mdpp.preprocessing_config.default_preprocessing_config.do.copy()
config.do.update({"remove_outliers": None, "difference_transform": True, "standardize": "standardize"})
data_preprocessed, inverse_config = mdpp.preprocess_data(df.values, config)
inverse_config.difference_transform = df.iloc[0, 0]
data_preprocessed_inverse = mdpp.preprocess_data_inverse(
data_preprocessed[:, 0], inverse_config
)
```
%package -n python3-mydatapreprocessing
Summary: Library/framework for making predictions.
Provides: python-mydatapreprocessing
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-mydatapreprocessing
# mydatapreprocessing
[](https://pypi.python.org/pypi/mydatapreprocessing/) [](https://badge.fury.io/py/mydatapreprocessing) [](https://pepy.tech/project/mydatapreprocessing) [](https://mybinder.org/v2/gh/Malachov/mydatapreprocessing/HEAD?filepath=demo.ipynb) [](https://lgtm.com/projects/g/Malachov/mydatapreprocessing/context:python) [](https://mydatapreprocessing.readthedocs.io/?badge=latest) [](https://opensource.org/licenses/MIT) [](https://codecov.io/gh/Malachov/mydatapreprocessing)
Load data from web link or local file (json, csv, Excel file, parquet, h5...), consolidate it (resample data, clean NaN values, do string embedding) derive new features via columns derivation and do preprocessing like
standardization or smoothing. If you want to see how functions works, check it's docstrings - working examples with printed results are also in tests - visual.py.
## Links
[Repo on GitHub](https://github.com/Malachov/mydatapreprocessing)
[Official readthedocs documentation](https://mydatapreprocessing.readthedocs.io)
## Installation
Python >=3.6 (Python 2 is not supported).
Install just with
```console
pip install mydatapreprocessing
```
There are some libraries that not every user will be using (for some specific data inputs for example). If you want to be sure to have all libraries, you can provide extras requirements like.
```console
pip install mydatapreprocessing[datatypes]
```
Available extras are ["all", "datasets", "datatypes"]
## Examples
You can use live [jupyter demo on binder](https://mybinder.org/v2/gh/Malachov/mydatapreprocessing/HEAD?filepath=demo.ipynb)
<!--phmdoctest-setup-->
```python
import mydatapreprocessing as mdp
import pandas as pd
import numpy as np
```
### Load data
You can use:
- python formats (numpy.ndarray, pd.DataFrame, list, tuple, dict)
- local files
- web urls
Supported path formats are:
- csv
- xlsx and xls
- json
- parquet
- h5
You can load more data at once in list.
Syntax is always the same.
<!--phmdoctest-label test_load_data-->
<!--phmdoctest-share-names-->
```python
data = mdp.load_data.load_data(
"https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv",
)
# data2 = mdp.load_data.load_data([PATH_TO_FILE.csv, PATH_TO_FILE2.csv])
```
### Consolidation
If you want to use data for some machine learning models, you will probably want to remove Nan values, convert string columns to numeric if possible, do encoding or keep only numeric data and resample.
Consolidation is working with pandas DataFrame as column names matters here.
There are many functions, but there is main function pipelining other functions `consolidate_data`
<!--phmdoctest-label test_consolidation-->
<!--phmdoctest-share-names-->
```python
consolidation_config = mdp.consolidation.consolidation_config.default_consolidation_config.do.copy()
consolidation_config.datetime.datetime_column = 'Date'
consolidation_config.resample.resample = 'M'
consolidation_config.resample.resample_function = "mean"
consolidation_config.dtype = 'float32'
consolidated = mdp.consolidation.consolidate_data(data, consolidation_config)
print(consolidated.head())
```
### Feature engineering
Functions in `feature_engineering` and `preprocessing` expects that data are in form (*n_samples*, *n_features*).
*n_samples* are usually much bigger and therefore transformed in `consolidate_data` if necessary.
In config, you can use shorter update dict syntax as all values names are unique.
### Feature engineering
Create new columns that can be for example used as another machine learning model input.
```python
import mydatapreprocessing.feature_engineering as mdpf
import mydatapreprocessing as mdp
data = pd.DataFrame(
[mdp.datasets.sin(n=30), mdp.datasets.ramp(n=30)]
).T
extended = mdpf.add_derived_columns(data, differences=True, rolling_means=10)
print(extended.columns)
print(f"\nit has less rows then on input {len(extended)}")
```
Functions in `feature_engineering` and `preprocessing` expects that data are in form (n_samples, n_features). n_samples are usually much bigger and therefore transformed in `consolidate_data`
if necessary.
### Preprocessing
Preprocessing can be used on pandas DataFrame as well as on numpy array. Column names are not important as it's just matrix with defined dtype.
There is many functions, but there is main function pipelining other functions `preprocess_data` Preprocessed data can be converted back with `preprocess_data_inverse`
<!--phmdoctest-label test_preprocess_data-->
<!--phmdoctest-share-names-->
```python
from mydatapreprocessing import preprocessing as mdpp
df = pd.DataFrame(np.array([range(5), range(20, 25), np.random.randn(5)]).astype("float32").T)
df.iloc[2, 0] = 500
config = mdpp.preprocessing_config.default_preprocessing_config.do.copy()
config.do.update({"remove_outliers": None, "difference_transform": True, "standardize": "standardize"})
data_preprocessed, inverse_config = mdpp.preprocess_data(df.values, config)
inverse_config.difference_transform = df.iloc[0, 0]
data_preprocessed_inverse = mdpp.preprocess_data_inverse(
data_preprocessed[:, 0], inverse_config
)
```
%package help
Summary: Development documents and examples for mydatapreprocessing
Provides: python3-mydatapreprocessing-doc
%description help
# mydatapreprocessing
[](https://pypi.python.org/pypi/mydatapreprocessing/) [](https://badge.fury.io/py/mydatapreprocessing) [](https://pepy.tech/project/mydatapreprocessing) [](https://mybinder.org/v2/gh/Malachov/mydatapreprocessing/HEAD?filepath=demo.ipynb) [](https://lgtm.com/projects/g/Malachov/mydatapreprocessing/context:python) [](https://mydatapreprocessing.readthedocs.io/?badge=latest) [](https://opensource.org/licenses/MIT) [](https://codecov.io/gh/Malachov/mydatapreprocessing)
Load data from web link or local file (json, csv, Excel file, parquet, h5...), consolidate it (resample data, clean NaN values, do string embedding) derive new features via columns derivation and do preprocessing like
standardization or smoothing. If you want to see how functions works, check it's docstrings - working examples with printed results are also in tests - visual.py.
## Links
[Repo on GitHub](https://github.com/Malachov/mydatapreprocessing)
[Official readthedocs documentation](https://mydatapreprocessing.readthedocs.io)
## Installation
Python >=3.6 (Python 2 is not supported).
Install just with
```console
pip install mydatapreprocessing
```
There are some libraries that not every user will be using (for some specific data inputs for example). If you want to be sure to have all libraries, you can provide extras requirements like.
```console
pip install mydatapreprocessing[datatypes]
```
Available extras are ["all", "datasets", "datatypes"]
## Examples
You can use live [jupyter demo on binder](https://mybinder.org/v2/gh/Malachov/mydatapreprocessing/HEAD?filepath=demo.ipynb)
<!--phmdoctest-setup-->
```python
import mydatapreprocessing as mdp
import pandas as pd
import numpy as np
```
### Load data
You can use:
- python formats (numpy.ndarray, pd.DataFrame, list, tuple, dict)
- local files
- web urls
Supported path formats are:
- csv
- xlsx and xls
- json
- parquet
- h5
You can load more data at once in list.
Syntax is always the same.
<!--phmdoctest-label test_load_data-->
<!--phmdoctest-share-names-->
```python
data = mdp.load_data.load_data(
"https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv",
)
# data2 = mdp.load_data.load_data([PATH_TO_FILE.csv, PATH_TO_FILE2.csv])
```
### Consolidation
If you want to use data for some machine learning models, you will probably want to remove Nan values, convert string columns to numeric if possible, do encoding or keep only numeric data and resample.
Consolidation is working with pandas DataFrame as column names matters here.
There are many functions, but there is main function pipelining other functions `consolidate_data`
<!--phmdoctest-label test_consolidation-->
<!--phmdoctest-share-names-->
```python
consolidation_config = mdp.consolidation.consolidation_config.default_consolidation_config.do.copy()
consolidation_config.datetime.datetime_column = 'Date'
consolidation_config.resample.resample = 'M'
consolidation_config.resample.resample_function = "mean"
consolidation_config.dtype = 'float32'
consolidated = mdp.consolidation.consolidate_data(data, consolidation_config)
print(consolidated.head())
```
### Feature engineering
Functions in `feature_engineering` and `preprocessing` expects that data are in form (*n_samples*, *n_features*).
*n_samples* are usually much bigger and therefore transformed in `consolidate_data` if necessary.
In config, you can use shorter update dict syntax as all values names are unique.
### Feature engineering
Create new columns that can be for example used as another machine learning model input.
```python
import mydatapreprocessing.feature_engineering as mdpf
import mydatapreprocessing as mdp
data = pd.DataFrame(
[mdp.datasets.sin(n=30), mdp.datasets.ramp(n=30)]
).T
extended = mdpf.add_derived_columns(data, differences=True, rolling_means=10)
print(extended.columns)
print(f"\nit has less rows then on input {len(extended)}")
```
Functions in `feature_engineering` and `preprocessing` expects that data are in form (n_samples, n_features). n_samples are usually much bigger and therefore transformed in `consolidate_data`
if necessary.
### Preprocessing
Preprocessing can be used on pandas DataFrame as well as on numpy array. Column names are not important as it's just matrix with defined dtype.
There is many functions, but there is main function pipelining other functions `preprocess_data` Preprocessed data can be converted back with `preprocess_data_inverse`
<!--phmdoctest-label test_preprocess_data-->
<!--phmdoctest-share-names-->
```python
from mydatapreprocessing import preprocessing as mdpp
df = pd.DataFrame(np.array([range(5), range(20, 25), np.random.randn(5)]).astype("float32").T)
df.iloc[2, 0] = 500
config = mdpp.preprocessing_config.default_preprocessing_config.do.copy()
config.do.update({"remove_outliers": None, "difference_transform": True, "standardize": "standardize"})
data_preprocessed, inverse_config = mdpp.preprocess_data(df.values, config)
inverse_config.difference_transform = df.iloc[0, 0]
data_preprocessed_inverse = mdpp.preprocess_data_inverse(
data_preprocessed[:, 0], inverse_config
)
```
%prep
%autosetup -n mydatapreprocessing-3.0.3
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-mydatapreprocessing -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Mon May 15 2023 Python_Bot <Python_Bot@openeuler.org> - 3.0.3-1
- Package Spec generated
|
